Assessing Heterogeneity of Treatment Effects in Observational Studies

Am J Epidemiol. 2021 Jun 1;190(6):1088-1100. doi: 10.1093/aje/kwaa235.

Abstract

Here we describe methods for assessing heterogeneity of treatment effects over prespecified subgroups in observational studies, using outcome-model-based (g-formula), inverse probability weighting, doubly robust, and matching estimators of subgroup-specific potential outcome means, conditional average treatment effects, and measures of heterogeneity of treatment effects. We compare the finite-sample performance of different estimators in simulation studies where we vary the total sample size, the relative frequency of each subgroup, the magnitude of treatment effect in each subgroup, and the distribution of baseline covariates, for both continuous and binary outcomes. We find that the estimators' bias and variance vary substantially in finite samples, even when there is no unobserved confounding and no model misspecification. As an illustration, we apply the methods to data from the Coronary Artery Surgery Study (August 1975-December 1996) to compare the effect of surgery plus medical therapy with that of medical therapy alone for chronic coronary artery disease in subgroups defined by previous myocardial infarction or left ventricular ejection fraction.

Keywords: causal inference; effect-measure modification; heterogeneity of treatment effects; observational studies; subgroup analysis.

Publication types

  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, P.H.S.

MeSH terms

  • Cardiac Surgical Procedures
  • Cardiovascular Agents / therapeutic use
  • Combined Modality Therapy
  • Computer Simulation
  • Coronary Artery Disease / therapy
  • Data Interpretation, Statistical*
  • Humans
  • Models, Statistical*
  • Observational Studies as Topic / methods
  • Observational Studies as Topic / statistics & numerical data*
  • Outcome Assessment, Health Care / methods
  • Outcome Assessment, Health Care / statistics & numerical data*
  • Probability
  • Sample Size
  • Statistics as Topic / methods*
  • Treatment Outcome

Substances

  • Cardiovascular Agents